Skip to content

Instantly share code, notes, and snippets.


James McDermott jmmcd

View GitHub Profile
jmmcd /
Last active Dec 1, 2016 — forked from karpathy/
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
I've converted to Python 3, added command-line args, added slightly
more informative episode status message, allowed reloading of running
reward, episode number, and elapsed time, and switched off the
per-point status message -- jmmcd.
jmmcd /
Last active Dec 30, 2015
Snippet for reading in a table of numbers and predicting the last column as a function of the others, using either just a constant, or linear regression, or linear regression regularised with the elastic net. Uses Numpy and Scikit-learn.
#!/usr/bin/env python
from __future__ import print_function
import numpy as np
from sklearn.linear_model import ElasticNet, LinearRegression
import sys
# James McDermott (c) 2013
# Hosted at
# Requires Numpy and Scikit-learn
You can’t perform that action at this time.